This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Shape From Texture: Integrating Texture-Element Extraction and Surface Estimation
December 1989 (vol. 11 no. 12)
pp. 1233-1251

A method is presented for identifying texture elements while simultaneously recovering the orientation of textured surfaces. A multiscale region detector, based on measurements in a Del /sup 2/G (Laplacian-of-Gaussian) scale space, is used to construct a set of candidate texture elements. True elements are selected from the set of candidate elements by finding the planar surface that best predicts the observed areas of the latter. Results are shown for a variety of natural textures, including waves, flowers, rocks, clouds, and dirt clods.

[1] J. Aloimonos and M. Swain, "Shape from texture," inProc 9th Int. Joint Conf. AI, 1985, pp. 926-931.
[2] J. Aloimonos, "Detection of surface orientation from texture I: The case of planes," inProc. IEEE Conf. Computer Vision and Pattern Recognition, 1986, pp. 584-593.
[3] R. Bajcsy and L. Lieberman, "Texture gradient as a depth cue,"Comput. Graphics Image Processing, vol. 5, pp. 52-67, 1976.
[4] D. Blostein, "Recovering the orientation of textured surfaces in natural scenes," Ph.D. dissertation, Univ. Illinois, Coordinated Science Lab. Rep. UILU-ENG-87-2219, Apr. 1987.
[5] D. Blostein and N. Ahuja, "Representation and three-dimensional interpretation of image texture: An integrated approach," inProc. IEEE First Int. Conf. Computer Vision, June 1987, pp. 444-449.
[6] D. Blostein and N. Ahuja, "A multi-scale region detector,"Comput. Vision, Graphics, Image Processing, vol. 45, no. 1, pp. 22-41, Jan. 1989.
[7] M. L. Braunstein and J. W. Payne, "Perspective and form ratio as determinants of relative slant judgments,"J. Exp. Psychol., vol. 81, no. 3, pp. 584-590, 1969.
[8] J. Crowley and A. Parker, "A representation for shape based on peaks and ridges in the difference of low pass transform,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-6, no. 2, pp. 156-170, Mar. 1984.
[9] J. E. Cutting and R. T. Millard, "Three gradients and the perception of flat and curved surfaces,"J. Exp. Psychol.: General, vol. 113, no. 2, pp. 198-216, 1984.
[10] L. Davis, L. Janos, and S. Dunn, "Efficient recovery of shape from texture,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-5, no. 5, pp. 485-492, Sept. 1983.
[11] J. Gibson,The Perception of the Visual World. Boston, MA: Houghton Mifflin, 1950.
[12] K. Ikeuchi, "Shape from regular patterns (an example of constraint propagation in vision)," MIT A.I. Memo 567, Mar. 1980.
[13] K. Kanatani, "Detection of surface orientation and motion from texture by a stereological technique,"Artificial Intell., vol. 23, pp. 213-237, 1984.
[14] K. Kanatani and T. Chou, "Shape from texture: General principle," inProc. IEEE Conf. Computer Vision and Pattern Recognition 86, Miami, FL, June 1986, pp. 578-583.
[15] J. R. Kender, "Shape from texture," Ph.D. dissertation, Carnegie-Mellon Univ., Pittsburgh, PA, Rep. CMU-CS-81-102, Nov. 1980.
[16] H. Nakatani, S. Kimura, O. Saito, and T. Kitahashi, "Extraction of vanishing point and its application to scene analysis based on image sequence," inProc. Int. Conf. Pattern Recognition, 1980, pp. 370- 372.
[17] R. Nevatia and K. R. Babu, "Linear feature extraction and description,"Comput. Graphics Image Processing, vol. 13, pp. 257-269, 1980.
[18] Y. Ohta, K. Maenobu, and T. Sakai, "Obtaining surface orientation from texels under perspective projection," inProc. Int. Joint Conf. Artificial Intelligence, 1981, pp. 746-751.
[19] R. J. Phillips, "Stationary visual texture and the estimation of slant angle,"Quart. J. Psychol., vol. 22, pp. 389-397, 1970.
[20] A. Rosenfeld, "A note on automatic detection of texture gradients,"IEEE Trans. Comput., vol. C-24, pp. 988-991, Oct. 1975.
[21] R. R. Rosinski, "On the ambiguity of visual stimulation: A reply to Eriksson,"Perception Psychophys., vol. 16, no. 2, pp. 259-263, 1974.
[22] R. Rosinski and N. Levine, "Texture gradient effectiveness in the perception of surface slant,"J. Exp. Child Psychol., vol. 22, pp. 261-271, 1976.
[23] K. A. Stevens, "Slant-tilt: The visual encoding of surface orientation,"Biol. Cybern., vol. 46, pp. 183-195, 1983.
[24] D. Vickers, "Perceptual economy and the impression of visual depth,"Perception and Psychophys., vol. 10, no. 1, pp. 23-27, 1971.
[25] H. Voorhees and T. Poggio, "Detecting textons and texture boundaries in natural textures," inProc. IEEE First Int. Conf. Computer Vision, June 1987, pp. 25-258.
[26] A. P. Witkin, "Recovering surface shape and orientation from texture,"Artificial Intell., vol. 17, pp. 17-45, 1981.
[27] A. P. Witkin, "Scale space filtering," inProc. Eighth Int. Joint Conf. Artificial Intelligence, Karlsruhe, West Germany, Aug. 1983, pp. 1019- 1022.

Index Terms:
surface orientation estimation; texture element identification; Laplacian-of-Gaussian scale space; Del /sup 2/G scale space; texture-element extraction; multiscale region detector; waves; flowers; rocks; clouds; dirt clods; pattern recognition; picture processing
Citation:
D. Blostein, N. Ahuja, "Shape From Texture: Integrating Texture-Element Extraction and Surface Estimation," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 11, no. 12, pp. 1233-1251, Dec. 1989, doi:10.1109/34.41363
Usage of this product signifies your acceptance of the Terms of Use.